Stereo pair images from very high-resolution optical satellites GeoEye-1 (GE1) and WorldView-2 (WV2) can be succesfully used for land cover classification agricultural areas through object-based image analysis. The overall accuracy attained by applying nearest neighbor and support vector machine classifiers to the four multispectral bands of GE1 were very similar to those computed from WV2, for either four or eight multispectral bands. Height data, in the form of nDSM, proved to be the most important feature for greenhouse classification. We obtained overall accuracy close to 90%.
Source:
M.Á. Aguilar, F. Bianconi, F.J. Aguilar and I. Fernández, "Object-Based Greenhouse Classification from GeoEye-1 and WorldView-2 Stereo Imagery", Remote Sensing, 6(5):3554-3582, 2014
M.Á. Aguilar, F. Bianconi, F.J. Aguilar and I. Fernández, "Object-Based Greenhouse Classification from GeoEye-1 and WorldView-2 Stereo Imagery", Remote Sensing, 6(5):3554-3582, 2014
